The Optical Camera Communication (OCC) technology allows Visible Light Communications (VLC), one of the key technologies for the Sixth Generation (6G) of mobile communications, to be used with image sensors on the receiver side. For Screen-to-Camera (S2C) applications, in which Light Emitting Diode (LED) screens are used to send information symbols, increasing either (transmitted) image resolution or video frame rate may negatively impact the bit error performance and the visual quality of the OCC-encoded videos. This work proposes a completely new OCC/S2C transmission and reception system, in which it is possible to recover both the transmitted symbols and to restore the video quality at the same time. For this dual-task, a Parallel Factor Analysis (PARAFAC) decomposition is applied to model an OCC system for the first time in the literature. Computational simulations corroborate the correct formulation of the proposed models, propositions and algorithms, in addition to demonstrating that increasing the number of frames of the OCC-encoded video can generate diversity gains. This work also includes discussion on the practical aspects of data rate, data volume, and computational complexity of the receiver, accordingly to the system’s parameters.

Accurate short-term load forecasting is essential to the modern power system and smart grids; the utility can better implement demand-side management and operate the power system stable with a reliable forecasting system. The load demand contains a variety of different load components, and different loads operate with different frequencies. Conventional load forecasting models (linear regression (LR), Auto-Regressive Integrated Moving Average (ARIMA), deep neural network, etc.) ignore frequency domain and can only use time-domain load demand as inputs. To make full use of both time domain and frequency domain features of the load demand, a hybrid component decomposition and deep neural network load forecasting model is proposed in this paper. The proposed model first filters noises via wavelet-based denoising technique, then decomposes the original load demand into several sublayers to show the frequency features while the time domain information is preserved as well. Then bidirectional LSTM model is trained for each sub-layer independently. To better tunning the hyperparameters, a Bayesian hyperparameter optimization algorithm is adopted in this paper. Three case studies are designed to evaluate the performance of the proposed model. From the results, it is found that the proposed model improves RMSE by 66.59% and 84.06%, comparing to other load forecasting models.

As a highly dynamic operating process, flight activity requires a lot of attention from pilots. Thus, it’s quite imperative to give research to their visual attention. Traditional research methods mostly based on qualitative analysis, or hypothetical model, and seldom put context information into their model. However, the underlying knowledge (tacit knowledge) hidden in the different performances of pilot’s attention allocation is context related, and is hard to express by experts, thus it is difficult to use those traditional methods to construct an interaction system. In this paper, we mined attention pattern with scene context to achieve the quantitative analysis of tacit knowledge of pilots during flight tasks, and use the method of data mining as well as attribute graph model to construct visual cognitive graph(s). The attribute graph model was adopted to construct visual cognitive graphs which associate the obtained visual information within the flight context. Based on the model, the attention pattern with scene context was mined to achieve the quantitative analysis of tacit knowledge of pilots during flight tasks. Besides, three physical quantities derived from graph theory was introduced to describe the tacit knowledge, which can be used directly to construct an interaction system: first, key information, which shown as central node in the graph we built, reveals the most important information during flight mission within context; second, relevant information, which contains several nodes that was closely connected and strongly impact the central node, reveals the factors affecting the key information; third, bridge information based on betweenness centrality, which can be regard as the important information bridge(s), reveals the process of decision making. Our work can be directly used to train novice pilots, to guide the interface design, and to construct the adaptive interaction system.

The circuit design method and control strategy of a variable-frequency inductive charger are introduced. The target application is low-power inductive charging systems where the coupling coefficient is relatively stable, e.g., mobile phone chargers with mechanical positioning aids. On the transmitter side, a high-order compensation circuit is deployed to achieve a monotonous frequency-power relation, which allows the output power to be regulated by frequency tuning. Only a half-bridge inverter is required and soft switching is achievable at most operating points. On the receiver side, the load impedance is fixed around the optimal value to improve the energy efficiency. Experimental results show that with low-loss circuit components, the proposed scheme achieves good efficiency performance under full and partial loads.

The utility-scale co-located hybrid power plants (HPPs) have been receiving attention globally due to enhanced controllability and efficient utilization of electrical infrastructure. While power plant control has been extensively studied for single-technology power plants in the past decades, how to control a co-located HPP that includes sub-plants with multiple technologies is yet to be well defined. To fill the gap, this paper proposes a novel hierarchical control architecture for co-located HPPs. This control architecture contains four control levels: asset control level, plant control level, HPP control level and HPP energy management system (EMS) level. The objective of HPP EMS level is to find optimal strategies for market participation, and the objective of HPP control level is to execute those strategies from the HPP EMS in real time. The interactions across the control hierarchy are firstly discussed in this paper, where attention is closely paid to interactions between HPP EMS level and HPP control level, and between HPP control level and plant control level. Novel strategies for control coordination are presented to ensure all the control levels work together without counteracting against each other. Frequency control and fault ride-through are two examples to demonstrate such control coordination.

Spiking Neuron Network (SNN) has shown advantages in processing event-based data for image classification. However, the classification accuracy of SNNs decreases in noisy environment. The cascade spiking neuron network (cascade-SNN) was proposed to solve this problem in this letter. We used spiking convolutional spiking neuron network (SCNN) for features extraction and liquid state machine (LSM) for read out. Compared with early works on ANNs, this network achieved the state-of-the-art classification accuracy in DVS-CIFAR10 dataset and DVS-Gesture dataset, which are both challenging dataset because of noisy environment. We conducted ablation experiments to verify the proposed structure is effective and analyzed the influence of different hyper-parameters.

Internet of things (IoT) is transforming the way we imagine healthcare with ubiquitous connectivity, faster response and deeper personalized insights using large amounts of data. Fitness trackers provide useful insights to maintain balance of a healthy lifestyle. Nowadays, fitness trackers are available as wearable devices which creates a sense of unease in exercise and may cause skin irritation. In this paper, we present mmFiT, an edge computing enabled, contactless, real-time fitness tracker using a single mmwave radar point cloud data. It has the inherent advantage of user privacy preservation while tracking indoor fitness activities. Experimental results show that the system can classify various exercises with real-time accuracy of 95.53\% and is also capable of counting repetitions of exercises. This implementation is computationally inexpensive, and therefore, the system can be deployed in an IoT connected edge device for real-time operations. This system will be an ideal fit in a smart home or smart gymnasium setting.

Gate driver circuits to ensure proper turn-on and turn-off for power switches are essential parts of a power converter design. They become even more important for multilevel converters where multiple switches are operated at active voltage domains. Recent favorable use of Gallium-Nitride (GaN) devices for power switches makes gate driving even more challenging as the switch performance and reliability are more sensitive to variations of the gate driving signals and power compared with traditional power MOSFETs. This paper discusses gate driving methods using a multi-level multi-inductor hybrid (MIH) converter as the demonstration prototype to address two key challenges in designing gate drivers: 1) providing level-shifted PWM signals to active voltage domains and 2) powering schemes for gate driver circuits. To solve the first challenge, an optimal use of available half-bridge drivers is devised to eliminate the need for separate signal isolator chips. This method was implemented and verified in a MIH converter prototype for 48-V Point-of-Load (PoL) applications using three different powering schemes for gate drivers, including isolated power modules, regulated supplies from switch blocking voltages, and cascaded bootstrap power rails with regulations. The gate driver techniques and powering schemes are compared experimentally in terms of performance to illustrate their benefits and trade-offs.

The Third Generation Partnership Project (3GPP) recently released the 5G New Radio (NR) Vehicle-to-Everything (V2X) standard. NR-V2X is expected to support a large set of enhanced V2X applications, characterized by stringent requirements in terms of latency, reliability and data rate. The use of simulations plays a crucial role in the preliminary assessment of NR-V2X achievable performance, providing valuable insights on the strengths and limits of the new solution. This work introduces MoReV2X, an open-source ns-3 module for the simulation of NR-V2X communications. The development of MoReV2X adheres to 3GPP specifications, includes various traffic models, features an accurate implementation of the NR propagation channel between vehicles and allows to determine a thorough set of Key Performance Indicators (KPIs). A first set of exemplary results is reported to testify the proper functioning of the module. Moreover, the results reveal the impact that different subcarrier spacings have on system performance, when periodic and aperiodic traffic sources are considered.

This article is focused on providing some insight into the requirements for a non-contact continuous identity authentication system using radar sensing technologies. The article also discusses the basic principles supporting the potential new role of radar sensing technologies in a broad area of applications. It also highlights challenges associated with this new technology and provides some direction on what is needed to address requirements for real-world applications.

People with severe physical impairment such as amyotrophic lateral sclerosis (ALS) in a completely locked-in state (CLIS) suffer from inability to express their thoughts to others. To solve this problem, many brain-computer interface (BCI) systems have been developed, but they have not proven sufficient for CLIS. In this paper, we propose a word communication system: a BCI with partner assist, in which partners play an active role in helping patients express a word. We report here that five ALS patients in late stages (one in CLIS and four almost in CLIS) succeeded in expressing their own words (in Japanese) in response to wh-questions that could not be answered “yes/no.” Each subject sequentially selected vowels (maximum three) contained in the word that he or she wanted to express, by using a “yes/no” communication aid based on near-infrared spectroscopy. Then, a partner entered the selected vowels into a dictionary with vowel entries, which returned candidate words having those vowels. When there were no appropriate words, the partner changed one vowel and searched again or started over from the beginning. When an appropriate word was selected, it was confirmed by the subject via “yes/no” answers. Two subjects confirmed the selected word six times out of eight (credibility of 91.0% by a statistical measure); two subjects, including the one in CLIS, did so five times out of eight (74.6%); and one subject did so three times out of four (81.3%). We have thus taken the first step toward a practical word communication system for such patients.

We have witnessed the continuing arms race between backdoor attacks and the corresponding defense strategies on Deep Neural Networks (DNNs). However, most state-of-the-art defenses rely on the statistical sanitization of inputs or latent DNN representations to capture trojan behavior. In this paper, we first challenge the robustness of many recently reported defenses by introducing a novel variant of the targeted backdoor attack, called low-confidence backdoor attack. Low-confidence attack inserts the backdoor by assigning uniformly distributed probabilistic labels to the poisoned training samples, and is applicable to many practical scenarios such as Federated Learning and model-reuse cases. We evaluate our attack against five state-of-the-art defense methods, viz., STRIP, Gradient-Shaping, Februus, ULP-defense and ABS-defense, under the same threat model as assumed by the respective defenses and achieve Attack Success Rates (ASRs) of 99\%, 63.73%, 91.2%, 80% and 100%, respectively. After carefully studying the properties of the state-of-the-art attacks, including low-confidence attacks, we present HaS-Net, a mechanism to securely train DNNs against a number of backdoor attacks under the data-collection scenario. For this purpose, we use a reasonably small healing dataset, approximately 2% to 15% the size of training data, to heal the network at each iteration. We evaluate our defense for different datasets—Fashion-MNIST, CIFAR-10, Celebrity Face, Consumer Complaint and Urban Sound—and network architectures—MLPs, 2D-CNNs, 1D-CNNs—and against several attack configurations—standard backdoor attacks, invisible backdoor attacks, label-consistent attack and all-trojan backdoor attack, including their low-confidence variants. Our experiments show that HaS-Nets can decrease ASRs from over 90% to less than 15%, independent of the dataset, attack configuration and network architecture.

Localization of sensor nodes in the Internet of Underwater Things (IoUT) is of considerable significance due to its various applications, such as navigation, data tagging, and detection of underwater objects. Therefore, in this paper, we propose a hybrid Bayesian multidimensional scaling (BMDS) based localization technique that can work on a fully hybrid IoUT network where the nodes can communicate using either optical, magnetic induction, and acoustic technologies. These communication technologies are already used for communication in the underwater environment; however, lacking localization solutions. Optical and magnetic induction communication achieves higher data rates for short communication. On the contrary, acoustic waves provide a low data rate for long-range underwater communication. The proposed method collectively uses optical, magnetic induction, and acoustic communication-based ranging to estimate the underwater sensor nodes’ final locations. Moreover, we also analyze the proposed scheme by deriving the hybrid Cramer-Rao lower bound (H-CRLB). Simulation results provide a complete comparative analysis of the proposed method with the literature.

The integration of small-scale PV systems (such as roof-top PVs) decreases the visibility of the power system since the real demand load is masked. Most of the rooftop systems are behind-the-meter and cannot be measured by the household smart meter. To overcome the challenges mentioned above, this paper proposes an online solar energy disaggregation system to decouple the solar energy generated by the roof-top PV systems and ground truth demand load from the net measurements. A 1D CNN bidirectional long short-term memory (CNN-BiLSTM) deep learning method is used as the core algorithm of the proposed system. The system takes a wide range of online information (AMI data, meteorological data, satellite-driven irradiance, and temporal information) as inputs to evaluate the PV generation, and the system also enables online and offline modes. The effectiveness of the proposed algorithm is evaluated by comparing it to baselines. The results show that the proposed method reaches good performance under different penetration rates and different feeder levels. Finally, a transfer learning process is introduced to verify the proposed system has good robustness and can be applied to anywhere else easily.

The purpose of feeder-level energy disaggregation is to decouple the net load measured at the feeder-head into various components. This technology is vital for power system utilities since increased visibility of controllable loads enables the realization of demand-side management strategies. However, energy disaggregation at the feeder level is difficult to realize since the high-penetration of embedded generation masks the actual demand and different loads are highly aggregated. In this paper, the solar energy at the grid supply point is separated from the net load at first via either an unsupervised upscaling method or the supervised gradient boosting regression tree (GBRT) method. To deal with the uncertainty of the load components, the probabilistic energy disaggregation models based on multi-quantile recurrent neural network model (multi-quantile long short-term memory (MQ-LSTM) model and multi-quantile gated recurrent unit (MQ-GRU) model) are proposed to disaggregate the demand load into controlled loads (TCLs), non-thermostatically controlled loads (non-TCLs), and non-controllable loads. A variety of relevant information, including feeder measurements, meteorological measurements, calendar information, is adopted as the input features of the model. Instead of providing point prediction, the probabilistic model estimates the conditional quantiles and provides prediction intervals. A comprehensive case study is implemented to compare the proposed model with other state-of-the-art models (multi-quantile convolutional neural network (MQ-CNN), quantile gradient boosting regression tree (Q-GBRT), Quantile Light gradient boosting machine (Q-LGB)) from training time, reliability, sharpness, and overall performance aspects. The result shows that the MQ-LSTM can estimate reliable and sharp Prediction Intervals for target load components. And it shows the best performance among all algorithms with the shortest training time. Finally, a transfer learning algorithm is proposed to overcome the difficulty to obtain enough training data, and the model is pre-trained via synthetic data generated from a public database and then tested on the local dataset. The result confirms that the proposed energy disaggregation model is transferable and can be applied to other feeders easily.

The advanced metering infrastructure (AMI) is a compulsory component of the future smart grid; it not only provides near real-time two-way communication between the consumers and the utility but also gives an opportunity to third parties to provide relevant value-added services to the consumers to improve the user satisfaction. However, existing services require the consumers share their private energy data with other parties, which has potential privacy risks. To better balance the excellent quality of the services and privacy guarantee, a novel differential private federated learning-based third-party service platform is proposed. Instead of sending the original energy data to the cloud server, the central server in the proposed scheme only collects the model parameters, which are trained locally inside the consumers’ houses. Then the collected parameters are aggregated differential privately to eliminate the identity of individuals, and the aggregated parameters are used to update the central model and improve the model performance. Furthermore, a novel attention-based bidirectional long short-term memory neural network model is adopted to make predictions. In the case study, a residential short term load forecasting task is implemented to evaluate the performance of the proposed model; from the simulation results, the conclusion is made that the proposed model can achieve similar accuracy as the typical centralized model and better control the privacy loss flexibly at the same time.

This work developed two-stage labeling models. The first stage is to process the text before execution by removing the suffixes attached to it. And then the second stage is to design models by applying mathematical models using Multilayer Perceptron (MPL), Full Recurrent Neural Network (FRNN), and Support Vector Machines (SVM). The current system helps classify words and allocate the correct parts of speech according to their wholesale position. To test the effectiveness of the proposed models using two different languages (Arabic and Hindi). The results showed the effectiveness of the proposed models is successfully solving the problem of clarification of words for the Arabic text. Also, compared to previous studies, the proposed models achieved high accuracy by classifying the parts of speech with an accuracy of up to (99%).

This paper introduces a new data analysis framework, called Integrated Statistical Learning (ISL) theory, which offers solutions to blend the “two cultures” into a coherent whole by establishing a link between them. Through examples, we describe the challenges and potential gains of this new integrated statistical thinking.